Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered structurally. The description adds genuinely non-obvious behavior: results come back newest-first, each row carries thread id, lead, timestamp, sender identity (teammate by name or AI), and text, which lets an agent follow up with get_texts. It does not mention the effective 50-row cap here, though the description does cover the row shape; that one truncation detail is the only real gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The scope and ordering constraint is front-loaded before the filter list, and the alternative-tool routing closes the description, which is the right order. The dense semicolon chain in the first sentence takes a second read, and the final note about search_what_was_said could be tightened, but no sentence is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description compensates by enumerating the fields each row returns, which is what an agent needs to decide whether to call get_texts or answer directly. Combined with the ordering guarantee, the visibility scope (threads this person sees), and the natural-language usage examples for a 0-required-parameter tool, an agent has everything needed to call this correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 86%, so the schema already explains every parameter, and the baseline is 3. The description adds real value by mapping colloquial intents to parameter values (direction ours/theirs, limit 1, from today) and by clarifying that query matches words in the text, the lead's name, or a phone number in any format — but that mostly restates the query field's schema text rather than extending it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (find text messages), the corpus it searches (threads this person sees), the default ordering (newest first), and the filterable dimensions (direction, words/name/phone, lead, date range). It also explicitly contrasts itself with get_texts (single thread) and search_what_was_said (cross-channel search), so an agent can place it among siblings without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use guidance by translating natural-language intents into parameter combinations: "who did we text last" = direction ours with limit 1, "who texted us today" = direction theirs from today. It also names the alternative (search_what_was_said) and the condition that should route the agent there instead, which is exactly the when-not guidance the dimension rewards.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.